About Me

Zehan Wang (王泽寒) is a PhD student in the College of Computer Science at Zhejiang University, supervised by Prof. Zhou Zhao. I have published 10+ first-author papers at the top international AI conferences such as NeurIPS/ICLR/ICML/CVPR. My current research interests broadly span two areas:

1. Unified Multimodal Perception (2D pixels, 3D geometry, language, audio)

2. Spatial Intelligence in Visual Content (From understanding to generation)

My research is supported by the Fundamental Research Project for Young Ph.D. students from NSFC (国家自然科学基金博士青年基金).

I am actively seeking collaboration opportunities in both academia and industry — feel free to reach out via email!

🔥 News

• 2025.05: We release Prior Depth Anything, estimate fine&complete metric depth with coarse&incomplete depth measurement.
• 2025.05: 2 paper accepted by ACL 2025! (T2A-Feedback)
• 2025.05: 1 paper accepted by ICML 2025! (Orient Anything)
• 2025.02: 2 papers accepted by CVPR 2025! (SpatialCLIP)
• 2025.01: 6 papers are accepted by ICLR 2025! (OmniBind)
• 2024.12: We release Orient Anything, the foundation model to estimate object orientation in images.
• 2024.10: 6 papers are accepted by NeurIPS 2024! (Chat-Scene and Ex-MCR)
• 2024.05: 2 papers are accepted by ICML 2024! (FreeBind)
• 2023.10: 1 paper is accepted by EMNLP 2023! (3DRP-Net)
• 2023.09: 1 paper is accepted by NeurIPS 2023! (C-MCR)
• 2023.06: 2 papers are accepted by ICCV 2023! (WS-3DVG)
• 2023.05: 1 paper are accepted by ACL 2023!

📝 Representative Publications

Unified Multimodal Perception

• Unified Representations: C-MCR (NeurIPS 2023), Ex-MCR (NeurIPS 2024), FreeBind (ICML 2024), OmniBind (ICLR 2025)

Spatial Intelligence in Visual Content

• Point Cloud Understanding: Chat-3D (NAACL 2023) / Chat-Scene (NeurIPS 2024) for 3D MLLM, 3DRP-Net (EMNLP 2023) / WS-3DVG (ICCV 2023) for 3D visual grounding.

• Spatial-aware Image Understanding: Orient Anything (ICML 2025), SpatialCLIP (CVPR 2025)

• Spatial-aware Image Generation: 6DoF-Gen (Working on), GenSpace (Working on)

Arxiv 2025

• Depth Anything with Any Prior. Zehan Wang, Siyu Chen, Lihe Yang, Jialei Wang, Ziang Zhang, Hengshuang Zhao, Zhou Zhao Arxiv, 2025
• The SoTA zero-shot depth estimation model that can integrate any form of depth measurement as prior.

ICML 2025

• Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models. Zehan Wang, Ziang Zhang, Tianyu Pang, Chao Du, Hengshuang Zhao, Zhou Zhao ICML, 2025
• The first zero-shot image-based object orientation estimation model.

CVPR 2025

• SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language. Zehan Wang, Sashuai zhou, Shaoxuan He, Haifeng Huang, Lihe Yang, Ziang Zhang, Xize Cheng, Shengpeng Ji, Tao Jin, Hengshuang Zhao, Zhou Zhao CVPR, 2025
• Improving spatial intelligence of MLLM by enhancing the CLIP visual representations.

NeurIPS 2024

• Chat-3d: Data-efficiently tuning large language model for universal dialogue of 3d scenes Zehan Wang*, Haifeng Huang*, Yang Zhao, Ziang Zhang, Zhou Zhao NAACL 2025
• Chat-scene: Bridging 3d scene and large language models with object identifiers Haifeng Huang*, Yilun Chen*, Zehan Wang*, Rongjie Huang, Runsen Xu, Tai Wang, Luping Liu, Xize Cheng, Yang Zhao, Jiangmiao Pang, Zhou Zhao NeurIPS 2024
• Series of state-of-the-art 3D MLLM for scene understanding.

ICLR 2025

• Omnibind: Large-scale omni multimodal representation via binding spaces Zehan Wang, Ziang Zhang, Hang Zhang, Luping Liu, Rongjie Huang, Xize Cheng, Hengshuang Zhao, Zhou Zhao ICLR 2025
• Large-scale 3D-audio-image-language representation models (7B–30B parameters) achieving SoTA performance on 13 benchmarks.

ICML 2024

• FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion Zehan Wang, Ziang Zhang, Xize Cheng, Rongjie Huang, Luping Liu, Zhenhui Ye, Haifeng Huang, Yang Zhao, Tao Jin, Peng Gao, Zhou Zhao ICML 2024
• Enhancing multimodal representations (e.g., ImageBind, InternVL) by freely fusing them in a unified space.

NeurIPS 2023

• Connecting Multi-modal Contrastive Representations Zehan Wang, Yang Zhao, Xize Cheng, Haifeng Huang, Jiageng Liu, Li Tang, Linjun Li, Yongqi Wang, Aoxiong Yin, Ziang Zhang, Zhou Zhao NeurIPS 2023
• Learning multimodal contrastive representations without requiring paired data.

Full Publication List

2025

• Arxiv 2025 Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models Zehan Wang, Ziang Zhang, Tianyu Pang, Chao Du, Hengshuang Zhao, Zhou Zhao
• Arxiv 2025 OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios Zehan Wang, Haifeng Huang, Yang Zhao, Ziang Zhang, Zhou Zhao
• CVPR 2025 SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language. Zehan Wang, Sashuai zhou, Shaoxuan He, Haifeng Huang, Lihe Yang, Ziang Zhang, Xize Cheng, Shengpeng Ji, Tao Jin, Hengshuang Zhao, Zhou Zhao
• CVPR 2025 [RoboGround: Robot Manipulation with Grounded Vision-Language Priors] Haifeng Huang, Xinyi Chen, Yilun Chen, Hao Li, Xiaoshen Han, Zehan Wang, Tai Wang, Jiangmiao Pang, Zhou Zhao
• NAACL 2025 Chat-3d: Data-efficiently tuning large language model for universal dialogue of 3d scenes Zehan Wang*, Haifeng Huang*, Yang Zhao, Ziang Zhang, Zhou Zhao
• WWW 2025 EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration Minjie Hong, Yan Xia, Zehan Wang, Jieming Zhu, Ye Wang, Sihang Cai, Xiaoda Yang, Quanyu Dai, Zhenhua Dong, Zhimeng Zhang, Zhou Zhao
• ICLR 2025 Omnibind: Large-scale omni multimodal representation via binding spaces Zehan Wang, Ziang Zhang, Hang Zhang, Luping Liu, Rongjie Huang, Xize Cheng, Hengshuang Zhao, Zhou Zhao
• ICLR 2025 Improving Long-Text Alignment for Text-to-Image Diffusion Models Luping Liu, Chao Du, Tianyu Pang, Zehan Wang, Chongxuan Li, Dong Xu
• ICLR 2025 OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup Xize Cheng, Siqi Zheng, Zehan Wang, Minghui Fang, Ziang Zhang, Rongjie Huang, Ziyang Ma, Shengpeng Ji, Jialong Zuo, Tao Jin, Zhou Zhao
• ICLR 2025 VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words? Xize Cheng, Ruofan Hu, Xiaoda Yang, Jingyu Lu, Dongjie Fu, Zehan Wang, Shengpeng Ji, Rongjie Huang, Boyang Zhang, Tao Jin, Zhou Zhao
• ICLR 2025 Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling Shengpeng Ji, Ziyue Jiang, Wen Wang, Yifu Chen, Minghui Fang, Jialong Zuo, Qian Yang, Xize Cheng, Zehan Wang, Ruiqi Li, Ziang Zhang, Xiaoda Yang, Rongjie Huang, Yidi Jiang, Qian Chen, Siqi Zheng, Zhou Zhao
• ICLR 2025 Diff-prompt: Diffusion-driven prompt generator with mask supervision Weicai Yan, Wang Lin, Zirun Guo, Ye Wang, Fangming Feng, Xiaoda Yang, Zehan Wang, Tao Jin

2024

• NeurIPS 2024 Chat-scene: Bridging 3d scene and large language models with object identifiers Haifeng Huang*, Yilun Chen*, Zehan Wang*, Rongjie Huang, Runsen Xu, Tai Wang, Luping Liu, Xize Cheng, Yang Zhao, Jiangmiao Pang, Zhou Zhao
• NeurIPS 2024 Extending multi-modal contrastive representations Ziang Zhang*, Zehan Wang*, Luping Liu, Rongjie Huang, Xize Cheng, Zhenhui Ye, Wang Lin, Huadai Liu, Haifeng Huang, Yang Zhao, Tao Jin, Siqi Zheng, Zhou Zhao
• NeurIPS 2024 MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes Zhenhui Ye, Tianyun Zhong, Yi Ren, Ziyue Jiang, Jiawei Huang, Rongjie Huang, Jinglin Liu, Jinzheng He, Chen Zhang, Zehan Wang, Xize Chen, Xiang Yin, Zhou Zhao
• NeurIPS 2024 Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT Le Zhuo, Ruoyi Du, Han Xiao, Yangguang Li, Dongyang Liu, Rongjie Huang, Wenze Liu, Lirui Zhao, Fu-Yun Wang, Zhanyu Ma, Xu Luo, Zehan Wang, Kaipeng Zhang, Xiangyang Zhu, Si Liu, Xiangyu Yue, Dingning Liu, Wanli Ouyang, Ziwei Liu, Yu Qiao, Hongsheng Li, Peng Gao
• NeurIPS 2024 Frieren: Efficient Video-to-Audio Generation with Rectified Flow Matching Yongqi Wang, Wenxiang Guo, Rongjie Huang, Jiawei Huang, Zehan Wang, Fuming You, Ruiqi Li, Zhou Zhao
• NeurIPS 2024 Action Imitation in Common Action Space for Customized Action Image Synthesis Wang Lin, Jingyuan Chen, Jiaxin Shi, Zirun Guo, Yichen Zhu, Zehan Wang, Tao Jin, Zhou Zhao, Fei Wu, YAN Shuicheng, Hanwang Zhang
• ICML 2024 FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion Zehan Wang, Ziang Zhang, Xize Cheng, Rongjie Huang, Luping Liu, Zhenhui Ye, Haifeng Huang, Yang Zhao, Tao Jin, Peng Gao, Zhou Zhao
• ICML 2024 InstructSpeech: Following Speech Editing Instructions via Large Language Models Rongjie Huang, Ruofan Hu, Yongqi Wang, Zehan Wang, Xize Cheng, Ziyue Jiang, Zhenhui Ye, Dongchao Yang, Luping Liu, Peng Gao, Zhou Zhao
• ACL 2024 Make-a-voice: Revisiting voice large language models as scalable multilingual and multitask learners Rongjie Huang, Chunlei Zhang, Yongqi Wang, Dongchao Yang, Jinchuan Tian, Zhenhui Ye, Luping Liu, Zehan Wang, Ziyue Jiang, Xuankai Chang, Jiatong Shi, Chao Weng, Zhou Zhao, Dong Yu
• ACL 2024 TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation Xize Cheng, Rongjie Huang, Linjun Li, Tao Jin, Zehan Wang, Aoxiong Yin, Minglei Li, Xinyu Duan, Zhou Zhao
• ACM MM 2024 VoiceTuner: Self-Supervised Pre-training and Efficient Fine-tuning For Voice Generation Rongjie Huang, Yongqi Wang, Ruofan Hu, Xiaoshan Xu, Zhiqing Hong, Dongchao Yang, Xize Cheng, Zehan Wang, Ziyue Jiang, Zhenhui Ye, Luping Liu, Siqi Zheng, Zhou Zhao

2023

• NeurIPS 2023 Connecting Multi-modal Contrastive Representations. Zehan Wang, Yang Zhao, Xize Cheng, Haifeng Huang, Jiageng Liu, Li Tang, Linjun Li, Yongqi Wang, Aoxiong Yin, Ziang Zhang, Zhou Zhao. NeurIPS 2023
• ICCV 2023 Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding. Zehan Wang, Haifeng Huang, Yang Zhao, Linjun Li, Xize Cheng, Yichen Zhu, Aoxiong Yin, Zhou Zhao. ICCV 2023
• ICCV 2023 MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition Xize Cheng, Tao Jin, Rongjie Huang, Linjun Li, Wang Lin, Zehan Wang, Ye Wang, Huadai Liu, Aoxiong Yin, Zhou Zhao. ICCV 2023
• EMNLP 2023 3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding Zehan Wang, Haifeng Huang, Yang Zhao, Linjun Li, Xize Cheng, Yichen Zhu, Aoxiong Yin, Zhou Zhao. EMNLP 2023
• ACL 2023 Scene-robust natural language video localization via learning domain-invariant representations Zehan Wang, Yang Zhao, Haifeng Huang, Yan Xia, Zhou Zhao. ACL 2023

📖 Educations

• 2022.09 - Present, Ph.D Student, Zhejiang University, Hangzhou.

• 2018.09 - 2022.06, Undergraduate, Zhejiang Univeristy, Hangzhou.

🎖 Honors and Awards

• 2025: Fundamental Research Project for Young Ph.D. students from NSFC (国家自然科学基金博士青年基金)
• 2022: Excellent Graduate, Zhejiang Province
• 2020: National Scholarships
• 2019: National Scholarships
• 2019, 2020, 2021: Zhejiang University First-class Scholarships